# Cross attentive pooling for speaker verification

arXiv: https://arxiv.org/abs/2008.05983 · HTML: https://mlsanity.com/paper/2008.05983/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 13 Aug 2020.

## Built on by (most cited first, 3 of 3)

- [Speaker embeddings by modeling channel-wise correlations](https://mlsanity.com/paper/2104.02571/) (2021)
- [Inclusive Speaker Verification with Adaptive thresholding](https://mlsanity.com/paper/2111.05501/) (2021)
- [Generalized Stock Price Prediction for Multiple Stocks Combined with News Fusion](https://mlsanity.com/paper/2603.19286/) (2026)

## Abstract (arXiv)

The goal of this paper is text-independent speaker verification where utterances come from 'in the wild' videos and may contain irrelevant signal. While speaker verification is naturally a pair-wise problem, existing methods to produce the speaker embeddings are instance-wise. In this paper, we propose Cross Attentive Pooling (CAP) that utilizes the context information across the reference-query pair to generate utterance-level embeddings that contain the most discriminative information for the pair-wise matching problem. Experiments are performed on the VoxCeleb dataset in which our method outperforms comparable pooling strategies.